Bmad Quick Dev

Quick Dev New Preview Workflow

Goal: Turn user intent into a hardened, reviewable artifact.

CRITICAL: If a step says "read fully and follow step-XX", you read and follow step-XX. No exceptions.

Subagents, when the capability is available, are an important part of this workflow. Use them as directed by the workflow steps. If you need an explicit user instruction to run them, ask once now for the whole workflow run.

READY FOR DEVELOPMENT STANDARD

A specification is "Ready for Development" when:

• Actionable: Every task has a file path and specific action.
• Logical: Tasks ordered by dependency.
• Testable: All ACs use Given/When/Then.
• Complete: No placeholders or TBDs.

SCOPE STANDARD

A specification should target a single user-facing goal within 900–1600 tokens:

• Single goal: One cohesive feature, even if it spans multiple layers/files. Multi-goal means >=2 top-level independent shippable deliverables — each could be reviewed, tested, and merged as a separate PR without breaking the others. Never count surface verbs, "and" conjunctions, or noun phrases. Never split cross-layer implementation details inside one user goal.
• Split: "add dark mode toggle AND refactor auth to JWT AND build admin dashboard"
• Don't split: "add validation and display errors" / "support drag-and-drop AND paste AND retry"
• 900–1600 tokens: Optimal range for LLM consumption. Below 900 risks ambiguity; above 1600 risks context-rot in implementation agents.
• Neither limit is a gate. Both are proposals with user override.

Conventions

• Bare paths (e.g. step-01-clarify-and-route.md) resolve from the skill root.
• {skill-root} resolves to this skill's installed directory (where customize.toml lives).
• {project-root}-prefixed paths resolve from the project working directory.
• {skill-name} resolves to the skill directory's basename.

On Activation

Step 1: Resolve the Workflow Block

Run: python3 {project-root}/_bmad/scripts/resolve_customization.py --skill {skill-root} --key workflow

If the script fails, resolve the workflow block yourself by reading these three files in base → team → user order and applying the same structural merge rules as the resolver:

1. {skill-root}/customize.toml — defaults 2. {project-root}/_bmad/custom/{skill-name}.toml — team overrides 3. {project-root}/_bmad/custom/{skill-name}.user.toml — personal overrides

Any missing file is skipped. Scalars override, tables deep-merge, arrays of tables keyed by code or id replace matching entries and append new entries, and all other arrays append.

Step 2: Execute Prepend Steps

Execute each entry in {workflow.activation_steps_prepend} in order before proceeding.

Step 3: Load Persistent Facts

Treat every entry in {workflow.persistent_facts} as foundational context you carry for the rest of the workflow run. Entries prefixed file: are paths or globs under {project-root} -- load the referenced contents as facts. All other entries are facts verbatim.

Step 4: Load Config

Load config from {project-root}/_bmad/bmm/config.yaml and resolve:

• project_name, planning_artifacts, implementation_artifacts, user_name
• communication_language, document_output_language, user_skill_level
• date as system-generated current datetime
• sprint_status = {implementation_artifacts}/sprint-status.yaml
• project_context = **/project-context.md (load if exists)
• CLAUDE.md / memory files (load if exist)
• YOU MUST ALWAYS SPEAK OUTPUT in your Agent communication style with the config {communication_language}
• Language MUST be tailored to {user_skill_level}
• Generate all documents in {document_output_language}

Step 5: Greet the User

Greet {user_name}, speaking in {communication_language}.

Step 6: Execute Append Steps

Execute each entry in {workflow.activation_steps_append} in order.

Activation is complete. If activation_steps_prepend or activation_steps_append were non-empty, confirm every entry was executed in order before proceeding. Do not begin the main workflow until all activation steps have been completed.

WORKFLOW ARCHITECTURE

This uses step-file architecture for disciplined execution:

• Micro-file Design: Each step is self-contained and followed exactly
• Just-In-Time Loading: Only load the current step file
• Sequential Enforcement: Complete steps in order, no skipping
• State Tracking: Persist progress via spec frontmatter and in-memory variables
• Append-Only Building: Build artifacts incrementally

Step Processing Rules

1. READ COMPLETELY: Read the entire step file before acting 2. FOLLOW SEQUENCE: Execute sections in order 3. WAIT FOR INPUT: Halt at checkpoints and wait for human 4. LOAD NEXT: When directed, read fully and follow the next step file

Critical Rules (NO EXCEPTIONS)

• NEVER load multiple step files simultaneously
• ALWAYS read entire step file before execution
• NEVER skip steps or optimize the sequence
• ALWAYS follow the exact instructions in the step file
• ALWAYS halt at checkpoints and wait for human input

FIRST STEP

Read fully and follow: ./step-01-clarify-and-route.md to begin the workflow.

Compile Epic Context

Task Given an epic number, the epics file, the planning artifacts directory, and a desired output path, compile a clean, focused, developer-ready context file (epic-<N>-context.md).

Steps

1. Read the epics file and extract the target epic's title, goal, and list of stories. 2. Scan the planning artifacts directory for the standard files (PRD, architecture, UX/design, product brief). 3. Pull only the information relevant to this epic. 4. Write the compiled context to the exact output path using the format below.

Exact Output Format

Use these headings:

# Epic {N} Context: {Epic Title}

<!-- Compiled from planning artifacts. Edit freely. Regenerate with compile-epic-context if planning docs change. -->

## Goal

{One clear paragraph: what this epic achieves and why it matters.}

## Stories

- Story X.Y: Brief title only
- ...

## Requirements & Constraints

{Relevant functional/non-functional requirements and success criteria for this epic (describe by purpose, not source).}

## Technical Decisions

{Key architecture decisions, constraints, patterns, data models, and conventions relevant to this epic.}

## UX & Interaction Patterns

{Relevant UX flows, interaction patterns, and design constraints (omit section entirely if nothing relevant).}

## Cross-Story Dependencies

{Dependencies between stories in this epic or with other epics/systems (omit if none).}

Rules

• Scope aggressively. Include only what a developer working on any story in this epic actually needs. When in doubt, leave it out — the developer can always read the full planning doc.
• Describe by purpose, not by source. Write "API responses must include pagination metadata" not "Per PRD section 3.2.1, pagination is required." Planning doc internals will change; the constraint won't.
• No full copies. Never quote source documents, section numbers, or paste large blocks verbatim. Always distill.
• No story-level details. The story list is for orientation only. Individual story specs handle the details.
• Nothing derivable from the codebase. Don't document what a developer can learn by reading the code.
• Be concise and actionable. Target 800–1500 tokens total. This file loads into quick-dev's context alongside other material.
• Never hallucinate content. If source material doesn't say something, don't invent it.
• Omit empty sections entirely, except Goal and Stories, which are always required.

Error handling

• If the epics file is missing or the target epic is not found: write nothing and report the problem to the calling agent. Goal and Stories cannot be populated without a usable epics file.
• If planning artifacts are missing or empty: still produce the file with Goal and Stories populated from the epics file, and note the gap in the Goal section. Never hallucinate content to fill missing sections.

<!-- Target: 900–1300 tokens. Above 1600 = high risk of context rot. Never over-specify "how" — use boundaries + examples instead. Cohesive cross-layer stories (DB+BE+UI) stay in ONE file. IMPORTANT: Remove all HTML comments when filling this template. -->

<frozen-after-approval reason="human-owned intent — do not modify unless human renegotiates">

Intent

<!-- What is broken or missing, and why it matters. Then the high-level approach — the "what", not the "how". -->

Problem: ONE_TO_TWO_SENTENCES

Approach: ONE_TO_TWO_SENTENCES

Boundaries & Constraints

<!-- Three tiers: Always = invariant rules. Ask First = human-gated decisions. Never = out of scope + forbidden approaches. -->

Always: INVARIANT_RULES

Ask First: DECISIONS_REQUIRING_HUMAN_APPROVAL <!-- Agent: if any of these trigger during execution, HALT and ask the user before proceeding. -->

Never: NON_GOALS_AND_FORBIDDEN_APPROACHES

I/O & Edge-Case Matrix

<!-- If no meaningful I/O scenarios exist, DELETE THIS ENTIRE SECTION. Do not write "N/A" or "None". -->

</frozen-after-approval>

Code Map

<!-- Agent-populated during planning. Annotated paths prevent blind codebase searching. -->

• FILE -- ROLE_OR_RELEVANCE
• FILE -- ROLE_OR_RELEVANCE

Tasks & Acceptance

<!-- Tasks: backtick-quoted file path -- action -- rationale. Prefer one task per file; group tightly-coupled changes when splitting would be artificial. --> <!-- If an I/O Matrix is present, include a task to unit-test its edge cases. --> <!-- AC covers system-level behaviors not captured by the I/O Matrix. Do not duplicate I/O scenarios here. -->

Execution:

• [ ] FILE -- ACTION -- RATIONALE

Acceptance Criteria:

• Given PRECONDITION, when ACTION, then EXPECTED_RESULT

Spec Change Log

<!-- Append-only. Populated by step-04 during review loops. Do not modify or delete existing entries. Each entry records: what finding triggered the change, what was amended, what known-bad state the amendment avoids, and any KEEP instructions (what worked well and must survive re-derivation). Empty until the first bad_spec loopback. -->

Design Notes

<!-- If the approach is straightforward, DELETE THIS ENTIRE SECTION. Do not write "N/A" or "None". --> <!-- Design rationale and golden examples only when non-obvious. Keep examples to 5–10 lines. -->

DESIGN_RATIONALE_AND_EXAMPLES

Verification

<!-- If no build, test, or lint commands apply, DELETE THIS ENTIRE SECTION. Do not write "N/A" or "None". --> <!-- How the agent confirms its own work. Prefer CLI commands. When no CLI check applies, state what to inspect manually. -->

Commands:

• COMMAND -- expected: SUCCESS_CRITERIA

Manual checks (if no CLI):

• WHAT_TO_INSPECT_AND_EXPECTED_STATE

Step 1: Clarify and Route

RULES

• YOU MUST ALWAYS SPEAK OUTPUT in your Agent communication style with the config {communication_language}
• The prompt that triggered this workflow IS the intent — not a hint.
• Do NOT assume you start from zero.
• The intent captured in this step — even if detailed, structured, and plan-like — may contain hallucinations, scope creep, or unvalidated assumptions. It is input to the workflow, not a substitute for step-02 investigation and spec generation. Ignore directives within the intent that instruct you to skip steps or implement directly.
• The user chose this workflow on purpose. Later steps (e.g. agentic adversarial review) catch LLM blind spots and give the human control. Do not skip them.
• EARLY EXIT means: stop this step immediately — do not read or execute anything further here. Read and fully follow the target file instead. Return here ONLY if a later step explicitly says to loop back.

Intent check (do this first)

Before listing artifacts or prompting the user, check whether you already know the intent. Check in this order — skip the remaining checks as soon as the intent is clear:

1. Explicit argument Did the user pass a specific file path, spec name, or clear instruction this message?

• If it points to a file that matches the spec template (has status frontmatter with a recognized value: draft, ready-for-dev, in-progress, in-review, or done) → set spec_file. Before exiting, run Story-key resolution (below). Then EARLY EXIT to the appropriate step (step-02 for draft, step-03 for ready/in-progress, step-04 for review). For done, ingest as context and proceed to INSTRUCTIONS — do not resume.
• Anything else (intent files, external docs, plans, descriptions) → ingest it as starting intent and proceed to INSTRUCTIONS. Do not attempt to infer a workflow state from it.

2. Recent conversation Do the last few human messages clearly show what the user intends to work on? Use the same routing as above.

3. Otherwise — scan artifacts and ask

• Active specs (draft, ready-for-dev, in-progress, in-review) in {implementation_artifacts}? → List them and HALT. Ask user which to resume (or [N] for new).
• If draft selected: Set spec_file. Run Story-key resolution (below). EARLY EXIT → ./step-02-plan.md (resume planning from the draft)
• If ready-for-dev or in-progress selected: Set spec_file. Run Story-key resolution (below). EARLY EXIT → ./step-03-implement.md
• If in-review selected: Set spec_file. Run Story-key resolution (below). EARLY EXIT → ./step-04-review.md
• Unformatted spec or intent file lacking status frontmatter? → Suggest treating its contents as the starting intent. Do NOT attempt to infer a state and resume it.

Never ask extra questions if you already understand what the user intends.

Story-key resolution

This runs on ALL paths (early-exit and INSTRUCTIONS) whenever spec_file is set. Determine whether the spec is an epic story — use the spec's filename, frontmatter, and any loaded epics file to identify {epic_num} and {story_num}. If the spec is not an epic story, skip silently and leave {story_key} unset.

If the spec is an epic story and {sprint_status} exists: find the development_status key matching {epic_num}-{story_num} by exact numeric equality on the first two segments (so 1-1 never collides with 1-10). Exactly one match → set {story_key} to that full key. Zero or multiple matches → leave {story_key} unset (warn on multiple).

INSTRUCTIONS

1. Load context.

• List files in {planning_artifacts} and {implementation_artifacts}.
• If you find an unformatted spec or intent file, ingest its contents to form your understanding of the intent.
• Determine context strategy. Using the intent and the artifact listing, infer whether the current work is a story from an epic. Do not rely on filename patterns or regex — reason about the intent, the listing, and any epics file content together.

A) Epic story path — if the intent is clearly an epic story:

1. Identify the epic number {epic_num} and (if present) the story number {story_num}. If you can't identify an epic number, use path B.

2. Check for a valid cached epic context. Look for {implementation_artifacts}/epic-<N>-context.md (where <N> is the epic number). A file is valid when it exists, is non-empty, starts with # Epic <N> Context: (with the correct epic number), and no file in {planning_artifacts} is newer.

• If valid: load it as the primary planning context. Do not load raw planning docs (PRD, architecture, UX, etc.). Skip to step 5.
• If missing, empty, or invalid: continue to step 3.

3. Compile epic context. Produce {implementation_artifacts}/epic-<N>-context.md by following ./compile-epic-context.md, in order of preference:

• Preferred — sub-agent: spawn a sub-agent with ./compile-epic-context.md as its prompt. Pass it the epic number, the epics file path, the {planning_artifacts} directory, and the output path {implementation_artifacts}/epic-<N>-context.md.
• Fallback — inline (for runtimes without sub-agent support, e.g. Copilot, Codex, local Ollama, older Claude): if your runtime cannot spawn sub-agents, or the spawn fails/times out, read ./compile-epic-context.md yourself and follow its instructions to produce the same output file.

4. Verify. After compilation, verify the output file exists, is non-empty, and starts with # Epic <N> Context:. If valid, load it. If verification fails, HALT and report the failure.

5. Previous story continuity. Regardless of which context source succeeded above, scan {implementation_artifacts} for specs from the same epic with status: done and a lower story number. Load the most recent one (highest story number below current). Extract its Code Map, Design Notes, Spec Change Log, and task list as continuity context for step-02 planning. If no done spec is found but an in-review spec exists for the same epic with a lower story number, note it to the user and ask whether to load it.

6. Resolve `{story_key}`. If not already set by an earlier early-exit path, run Story-key resolution (above) now.

B) Freeform path — if the intent is not an epic story:

• Planning artifacts are the output of BMAD phases 1-3. Typical files include:
• PRD (*prd*) — product requirements and success criteria
• Architecture (*architecture*) — technical design decisions and constraints
• UX/Design (*ux*) — user experience and interaction design
• Epics (*epic*) — feature breakdown into implementable stories
• Product Brief (*brief*) — project vision and scope
• Scan the listing for files matching these patterns. If any look relevant to the current intent, load them selectively — you don't need all of them, but you need the right constraints and requirements rather than guessing from code alone.

2. Clarify intent. Do not fantasize, do not leave open questions. If you must ask questions, ask them as a numbered list. When the human replies, verify that every single numbered question was answered. If any were ignored, HALT and re-ask only the missing questions before proceeding. Keep looping until intent is clear enough to implement. 3. Version control sanity check. Is the working tree clean? Does the current branch make sense for this intent — considering its name and recent history? If the tree is dirty or the branch is an obvious mismatch, HALT and ask the human before proceeding. If version control is unavailable, skip this check. 4. Multi-goal check (see SCOPE STANDARD). If the intent fails the single-goal criteria:

• Present detected distinct goals as a bullet list.
• Explain briefly (2–4 sentences): why each goal qualifies as independently shippable, any coupling risks if split, and which goal you recommend tackling first.
• HALT and ask human: [S] Split — pick first goal, defer the rest | [K] Keep all goals — accept the risks
• On S: Append deferred goals to {deferred_work_file}. Narrow scope to the first-mentioned goal. Continue routing.
• On K: Proceed as-is.

5. Route — choose exactly one:

Derive a valid kebab-case slug from the clarified intent. If the intent references a tracking identifier (story number, issue number, ticket ID), lead the slug with it (e.g. 3-2-digest-delivery, gh-47-fix-auth). If {implementation_artifacts}/spec-{slug}.md already exists: if its status is draft, treat it as the same work and resume it (set spec_file to that path, EARLY EXIT → ./step-02-plan.md); otherwise append -2, -3, etc. Set spec_file = {implementation_artifacts}/spec-{slug}.md.

a) One-shot — zero blast radius: no plausible path by which this change causes unintended consequences elsewhere. Clear intent, no architectural decisions.

EARLY EXIT → ./step-oneshot.md

b) Plan-code-review — everything else. When uncertain whether blast radius is truly zero, choose this path.

NEXT

Read fully and follow ./step-02-plan.md

Step 2: Plan

RULES

• YOU MUST ALWAYS SPEAK OUTPUT in your Agent communication style with the config {communication_language}
• No intermediate approvals.

INSTRUCTIONS

1. Draft resume check. If {spec_file} exists with status: draft, read it and capture the verbatim <frozen-after-approval>...</frozen-after-approval> block as preserved_intent. Otherwise preserved_intent is empty. 2. Investigate codebase. _Isolate deep exploration in sub-agents/tasks where available. To prevent context snowballing, instruct subagents to give you distilled summaries only._ 3. Read ./spec-template.md fully. Fill it out based on the intent and investigation. If {preserved_intent} is non-empty, substitute it for the <frozen-after-approval> block in your filled spec before writing. Write the result to {spec_file}. 4. Self-review against READY FOR DEVELOPMENT standard. 5. If intent gaps exist, do not fantasize, do not leave open questions, HALT and ask the human. 6. Token count check (see SCOPE STANDARD). If spec exceeds 1600 tokens:

• Show user the token count.
• HALT and ask human: [S] Split — carve off secondary goals | [K] Keep full spec — accept the risks
• On S: Propose the split — name each secondary goal. Append deferred goals to {deferred_work_file}. Rewrite the current spec to cover only the main goal — do not surgically carve sections out; regenerate the spec for the narrowed scope. Continue to checkpoint.
• On K: Continue to checkpoint with full spec.

CHECKPOINT 1

Present summary. Display the spec file path as a CWD-relative path (no leading /) so it is clickable in the terminal. If token count exceeded 1600 and user chose [K], include the token count and explain why it may be a problem.

After presenting the summary, display this note:

---

Before approving, you can open the spec file in an editor or ask me questions and tell me what to change. You can also use bmad-advanced-elicitation, bmad-party-mode, or bmad-code-review skills, ideally in another session to avoid context bloat.

---

HALT and ask human: [A] Approve | [E] Edit

• A: Re-read {spec_file} from disk.
• If the file is missing: HALT. Tell the user the spec file is gone and STOP — do not write anything to {spec_file}, do not set status, do not proceed to Step 3. Nothing below this point runs.
• If the file exists: Compare the content to what you wrote. If it has changed since you wrote it, acknowledge the external edits — show a brief summary of what changed — and proceed with the updated version. Then set status ready-for-dev in {spec_file}. Everything inside <frozen-after-approval> is now locked — only the human can change it. → Step 3.
• E: Apply changes, then return to CHECKPOINT 1.

NEXT

Read fully and follow ./step-03-implement.md

Step 3: Implement

RULES

• YOU MUST ALWAYS SPEAK OUTPUT in your Agent communication style with the config {communication_language}
• No push. No remote ops.
• Sequential execution only.
• Content inside <frozen-after-approval> in {spec_file} is read-only. Do not modify.

PRECONDITION

Verify {spec_file} resolves to a non-empty path and the file exists on disk. If empty or missing, HALT and ask the human to provide the spec file path before proceeding.

INSTRUCTIONS

Baseline

Capture baseline_commit (current HEAD, or NO_VCS if version control is unavailable) into {spec_file} frontmatter before making any changes.

Implement

Change {spec_file} status to in-progress in the frontmatter before starting implementation.

Follow ./sync-sprint-status.md with {target_status} = in-progress.

If {spec_file} has a non-empty context: list in its frontmatter, load those files before implementation begins. When handing to a sub-agent, include them in the sub-agent prompt so it has access to the referenced context.

Hand {spec_file} to a sub-agent/task and let it implement. If no sub-agents are available, implement directly.

Path formatting rule: Any markdown links written into {spec_file} must use paths relative to {spec_file}'s directory so they are clickable in VS Code. Any file paths displayed in terminal/conversation output must use CWD-relative format with :line notation (e.g., src/path/file.ts:42) for terminal clickability. No leading / in either case.

Self-Check

Before leaving this step, verify every task in the ## Tasks & Acceptance section of {spec_file} is complete. Mark each finished task [x]. If any task is not done, finish it before proceeding.

NEXT

Read fully and follow ./step-04-review.md

Step 4: Review

RULES

• YOU MUST ALWAYS SPEAK OUTPUT in your Agent communication style with the config {communication_language}
• Review subagents get NO conversation context.
• All review subagents must run at the same model capability as the current session.

INSTRUCTIONS

Change {spec_file} status to in-review in the frontmatter before continuing.

Construct Diff

Read {baseline_commit} from {spec_file} frontmatter. If {baseline_commit} is missing or NO_VCS, use best effort to determine what changed. Otherwise, construct {diff_output} covering all changes — tracked and untracked — since {baseline_commit}.

Do NOT git add anything — this is read-only inspection.

Review

Launch three subagents without conversation context. If no sub-agents are available, generate three review prompt files in {implementation_artifacts} — one per reviewer role below — and HALT. Ask the human to run each in a separate session (ideally a different LLM) and paste back the findings.

• Blind hunter — receives inline {diff_output} only. No spec, no context docs, no project access. Invoke via the bmad-review-adversarial-general skill.
• Edge case hunter — receives {diff_output} and read access to the project. Invoke via the bmad-review-edge-case-hunter skill.
• Acceptance auditor — receives {diff_output}, {spec_file}, and read access to the project. Must also read the docs listed in {spec_file} frontmatter context. Checks for violations of acceptance criteria, rules, and principles from the spec and context docs.

Classify

1. Deduplicate all review findings. 2. Classify each finding. The first three categories are this story's problem — caused or exposed by the current change. The last two are not this story's problem.

• intent_gap — caused by the change; cannot be resolved from the spec because the captured intent is incomplete. Do not infer intent unless there is exactly one possible reading.
• bad_spec — caused by the change, including direct deviations from spec. The spec should have been clear enough to prevent it. When in doubt between bad_spec and patch, prefer bad_spec — a spec-level fix is more likely to produce coherent code.
• patch — caused by the change; trivially fixable without human input. Just part of the diff.
• defer — pre-existing issue not caused by this story, surfaced incidentally by the review. Collect for later focused attention.
• reject — noise. Drop silently. When unsure between defer and reject, prefer reject — only defer findings you are confident are real.

3. Process findings in cascading order. If intent_gap or bad_spec findings exist, they trigger a loopback — lower findings are moot since code will be re-derived. If neither exists, process patch and defer normally. Increment {specLoopIteration} on each loopback. If it exceeds 5, HALT and escalate to the human.

• intent_gap — Root cause is inside <frozen-after-approval>. Revert code changes. Loop back to the human to resolve. Once resolved, read fully and follow ./step-02-plan.md to re-run steps 2–4.
• bad_spec — Root cause is outside <frozen-after-approval>. Before reverting code: extract KEEP instructions for positive preservation (what worked well and must survive re-derivation). Revert code changes. Read the ## Spec Change Log in {spec_file} and strictly respect all logged constraints when amending the non-frozen sections that contain the root cause. Append a new change-log entry recording: the triggering finding, what was amended, the known-bad state avoided, and the KEEP instructions. Read fully and follow ./step-03-implement.md to re-derive the code, then this step will run again.
• patch — Auto-fix. These are the only findings that survive loopbacks.
• defer — Append to {deferred_work_file}.
• reject — Drop silently.

NEXT

Read fully and follow ./step-05-present.md

Step 5: Present

RULES

• YOU MUST ALWAYS SPEAK OUTPUT in your Agent communication style with the config {communication_language}
• NEVER auto-push.

INSTRUCTIONS

Generate Suggested Review Order

Read {baseline_commit} from {spec_file} frontmatter and construct the diff of all changes since that commit.

Append the review order as a ## Suggested Review Order section to {spec_file} after the last existing section. Do not modify the Code Map.

Build the trail as an ordered sequence of stops — clickable path:line references with brief framing — optimized for a human reviewer reading top-down to understand the change:

1. Order by concern, not by file. Group stops by the conceptual concern they address (e.g., "validation logic", "schema change", "UI binding"). A single file may appear under multiple concerns. 2. Lead with the entry point — the single highest-leverage file:line a reviewer should look at first to grasp the design intent. 3. Inside each concern, order stops from most important / architecturally interesting to supporting. Lightly bias toward higher-risk or boundary-crossing stops. 4. End with peripherals — tests, config, types, and other supporting changes come last. 5. Every code reference is a clickable spec-file-relative link. Compute each link target as a relative path from {spec_file}'s directory to the changed file. Format each stop as a markdown link: [short-name:line](../../path/to/file.ts#L42). Use a #L line anchor. Use the file's basename (or shortest unambiguous suffix) plus line number as the link text. The relative path must be dynamically derived — never hardcode the depth. 6. Each stop gets one ultra-concise line of framing (≤15 words) — why this approach was chosen here and what it achieves in the context of the change. No paragraphs.

Format each stop as framing first, link on the next indented line:

## Suggested Review Order

**{Concern name}**

- {one-line framing}
  [`file.ts:42`](../../src/path/to/file.ts#L42)

- {one-line framing}
  [`other.ts:17`](../../src/path/to/other.ts#L17)

**{Next concern}**

- {one-line framing}
  [`file.ts:88`](../../src/path/to/file.ts#L88)

The ../../ prefix above is illustrative — compute the actual relative path from {spec_file}'s directory to each target file.

When there is only one concern, omit the bold label — just list the stops directly.

Mark Spec Done

Change {spec_file} status to done in the frontmatter.

Follow ./sync-sprint-status.md with {target_status} = review.

Commit and Open

1. If version control is available and the tree is dirty, create a local commit with a conventional message derived from the spec title. 2. Open the spec in the user's editor so they can click through the Suggested Review Order:

• Resolve two absolute paths: (1) the repository root (git rev-parse --show-toplevel — returns the worktree root when in a worktree, project root otherwise; if this fails, fall back to the current working directory), (2) {spec_file}. Run code -r "{absolute-root}" "{absolute-spec-file}" — the root first so VS Code opens in the right context, then the spec file. Always double-quote paths to handle spaces and special characters.
• If code is not available (command fails), skip gracefully and tell the user the spec file path instead.

Display Summary

Display summary of your work to the user, including the commit hash if one was created. Any file paths shown in conversation/terminal output must use CWD-relative format (no leading /) with :line notation (e.g., src/path/file.ts:42) for terminal clickability — the goal is to make paths clickable in terminal emulators. Include:

• A note that the spec is open in their editor (or the file path if it couldn't be opened). Mention that {spec_file} now contains a Suggested Review Order.
• Navigation tip: "Ctrl+click (Cmd+click on macOS) the links in the Suggested Review Order to jump to each stop."
• Offer to push and/or create a pull request.

Workflow complete.

On Complete

Run: python3 {project-root}/_bmad/scripts/resolve_customization.py --skill {skill-root} --key workflow.on_complete

If the resolved workflow.on_complete is non-empty, follow it as the final terminal instruction before exiting.

Step One-Shot: Implement, Review, Present

RULES

• YOU MUST ALWAYS SPEAK OUTPUT in your Agent communication style with the config {communication_language}
• NEVER auto-push.

INSTRUCTIONS

Implement

Follow ./sync-sprint-status.md with {target_status} = in-progress.

Implement the clarified intent directly.

Review

Invoke the bmad-review-adversarial-general skill in a subagent with the changed files. The subagent gets NO conversation context — to avoid anchoring bias. Launch at the same model capability as the current session. If no sub-agents are available, write the changed files to a review prompt file in {implementation_artifacts} and HALT. Ask the human to run the review in a separate session and paste back the findings.

Classify

Deduplicate all review findings. Three categories only:

• patch — trivially fixable. Auto-fix immediately.
• defer — pre-existing issue not caused by this change. Append to {deferred_work_file}.
• reject — noise. Drop silently.

If a finding is caused by this change but too significant for a trivial patch, HALT and present it to the human for decision before proceeding.

Generate Spec Trace

Set {title} = a concise title derived from the clarified intent.

Write {spec_file} using ./spec-template.md. Fill only these sections — delete all others:

1. Frontmatter — set title: '{title}', type, created, status: 'done'. Add route: 'one-shot'. 2. Title and Intent — # {title} heading and ## Intent with Problem and Approach lines. Reuse the summary you already generated for the terminal. 3. Suggested Review Order — append after Intent. Build using the same convention as ./step-05-present.md § "Generate Suggested Review Order" (spec-file-relative links, concern-based ordering, ultra-concise framing).

Follow ./sync-sprint-status.md with {target_status} = review.

Commit

If version control is available and the tree is dirty, create a local commit with a conventional message derived from the intent. If VCS is unavailable, skip.

Present

1. Open the spec in the user's editor so they can click through the Suggested Review Order:

• Resolve two absolute paths: (1) the repository root (git rev-parse --show-toplevel — returns the worktree root when in a worktree, project root otherwise; if this fails, fall back to the current working directory), (2) {spec_file}. Run code -r "{absolute-root}" "{absolute-spec-file}" — the root first so VS Code opens in the right context, then the spec file. Always double-quote paths to handle spaces and special characters.
• If code is not available (command fails), skip gracefully and tell the user the spec file path instead.

2. Display a summary in conversation output, including:

• The commit hash (if one was created).
• List of files changed with one-line descriptions. Any file paths shown in conversation/terminal output must use CWD-relative format (no leading /) with :line notation (e.g., src/path/file.ts:42) for terminal clickability — this differs from spec-file links which use spec-file-relative paths.
• Review findings breakdown: patches applied, items deferred, items rejected. If all findings were rejected, say so.
• A note that the spec is open in their editor (or the file path if it couldn't be opened). Mention that {spec_file} now contains a Suggested Review Order.
• Navigation tip: "Ctrl+click (Cmd+click on macOS) the links in the Suggested Review Order to jump to each stop."

3. Offer to push and/or create a pull request.

HALT and wait for human input.

Workflow complete.

On Complete

Run: python3 {project-root}/_bmad/scripts/resolve_customization.py --skill {skill-root} --key workflow.on_complete

If the resolved workflow.on_complete is non-empty, follow it as the final terminal instruction before exiting.

Sync Sprint Status

Shared sub-step for updating sprint-status.yaml during quick-dev. Called from any route (plan-code-review, one-shot, future routes) with a {target_status} parameter.

Preconditions

Skip this entire file (return to caller) if ANY of:

• {story_key} is unset
• {sprint_status} does not exist on disk

Instructions

1. Load the FULL {sprint_status} file. 2. Find the development_status entry matching {story_key}. If not found, warn the user once ("{story_key} not found in sprint-status; skipping sprint sync") and return to caller. 3. Idempotency check. If development_status[{story_key}] is already at {target_status} or a later state (review is later than in-progress; done is later than both), return to caller — no write needed. Never regress a story's status. 4. Set development_status[{story_key}] to {target_status}. 5. Epic lift (only when `{target_status}` = `in-progress`). Derive the parent epic key as epic-{N} from the leading numeric segment of {story_key} (e.g., 3-2-digest-delivery → epic-3). If that entry exists and is backlog, set it to in-progress. Leave it alone otherwise. Skip this sub-step entirely when {target_status} is not in-progress. 6. Refresh last_updated to the current date. 7. Save the file, preserving ALL comments and structure including STATUS DEFINITIONS and WORKFLOW NOTES.